Proxy Asset Generation for Cloth Simulation in Games
Zhongtian Zheng, Tongtong Wang, Qijia Feng, Zherong Pan, Xifeng Gao, Kui Wu
摘要
Simulating high-resolution cloth poses computational challenges in real-time applications. In the gaming industry, the proxy mesh technique offers an alternative, simulating a simplified low-resolution cloth geometry, proxy mesh. This proxy mesh's dynamics drive the detailed high-resolution geometry, visual mesh , through Linear Blended Skinning (LBS). However, generating a suitable proxy mesh with appropriate skinning weights from a given visual mesh is non-trivial, often requiring skilled artists several days for fine-tuning. This paper presents an automatic pipeline to convert an ill-conditioned highresolution visual mesh into a single-layer low-poly proxy mesh. Given that the input visual mesh may not be simulation-ready, our approach then simulates the proxy mesh based on specific use scenarios and optimizes the skinning weights, relying on differential skinning with several well-designed loss functions to ensure the skinned visual mesh appears plausible in the final simulation. We have tested our method on various challenging cloth models, demonstrating its robustness and effectiveness.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper11
- Neural Unsigned Distance Fields for Implicit Function LearningJulian Chibane, Aymen Mir, Gerard Pons-MollNeurIPS 2020 · 被引用 415 次
- RigNet: neural rigging for articulated charactersZhan Xu, Yang Zhou, Evangelos Kalogerakis, Chris Landreth 等SIGGRAPH 2020 · 被引用 127 次
- Projective dynamics with dry frictional contactMickaël Ly, Jean Jouve, Laurence Boissieux, Florence Bertails-DescoubesSIGGRAPH 2020 · 被引用 63 次
- GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance RepresentationSiyu Ren, Junhui Hou, Xiaodong Chen, Ying He 等ICCV 2023 · 被引用 53 次
- Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set ProjectionJunsheng Zhou, Baorui Ma, Shujuan Li, Yu-Shen Liu 等ICCV 2023 · 被引用 49 次
相关 Paper
- Progressive Dynamics for Cloth and Shell AnimationJiayi Eris Zhang, Doug L. James, Danny M. KaufmanSIGGRAPH 2024 · 被引用 7 次
- Rig-Reconstruct-Render (R33D): Collaborative Representation for Editable and Skeleton-Drivable 3D Asset GenerationYuxuan Xiong, Ye Chen, Yue Shi, Zhangli Hu 等ACM MM 2025
- Invertible Neural SkinningYash Kant, Aliaksandr Siarohin, Riza Alp Güler, Menglei Chai 等CVPR 2023
- AniMimic: Imitating 3D Animation from Video PriorsTianyi Xie, Yunuo Chen, Yaowei Guo, Yin Yang 等CVPR 2026
- Low-poly Mesh Generation for Building ModelsXifeng Gao, Kui Wu, Zherong PanSIGGRAPH 2022 · 被引用 23 次
